cstr
/

Octen-Embedding-0.6B-ONNX-INT8

Sentence Similarity

feature-extraction

Model card Files Files and versions

Octen-Embedding-0.6B-ONNX-INT8

2.15 GB

Ctrl+K

Ctrl+K

1 contributor

History: 10 commits

cstr's picture

docs: add provenance / EU AI Act Art. 53 note

3d68a23 verified 3 months ago

.gitattributes

1.69 kB
fix: replace broken vanilla INT8 with SmoothQuant α=0.8 (cos_min 0.64 → 0.99) 6 months ago
README.md

5.74 kB
docs: add provenance / EU AI Act Art. 53 note 3 months ago
added_tokens.json

707 Bytes
Upload folder using huggingface_hub 8 months ago
config.json

1.35 kB
Upload folder using huggingface_hub 8 months ago
merges.txt

1.67 MB
Upload folder using huggingface_hub 8 months ago
model.int8.onnx

5.45 MB
xet

Fix external_data.location: 'model.smoothed.int8.onnx.data' -> 'model.int8.onnx.data' so ORT can find the (renamed) .data file. The .data payload is unchanged. 6 months ago
model.int8.onnx.data

1.06 GB
xet

init: Octen-Embedding-0.6B SmoothQuant INT8 ONNX (alpha=0.8, cos=~0.92 vs PyTorch ref) 6 months ago
model.int8.vanilla.onnx

5.45 MB
xet

fix: replace broken vanilla INT8 with SmoothQuant α=0.8 (cos_min 0.64 → 0.99) 6 months ago
model.int8.vanilla.onnx.data

1.06 GB
xet

fix: replace broken vanilla INT8 with SmoothQuant α=0.8 (cos_min 0.64 → 0.99) 6 months ago
quantize_octen_int8.py

5.67 kB
Upload folder using huggingface_hub 8 months ago
special_tokens_map.json

613 Bytes
Upload folder using huggingface_hub 8 months ago
tokenizer.json

11.4 MB
xet

Upload folder using huggingface_hub 8 months ago
tokenizer_config.json

5.4 kB
Upload folder using huggingface_hub 8 months ago
vocab.json

2.78 MB
Upload folder using huggingface_hub 8 months ago